Create image generation

Use this interface to generate images from text prompts. The interface format is compatible with the OpenAI generations  protocol.

Authorization

Authorization

• Type: HTTP Bearer Auth, value type string
• Required
• Description: Used to verify account information. Go to API Console , click Create Token to obtain.

Authorization: Bearer <YOUR_API_KEY>

Request Headers

Content-Type

• Type: enum<string>
• Required, fixed value application/json
• Description: The media type of the request body. Must be application/json.

Request Body

Overview

model

• Type: string
• Required
• Description: The image model to use.
• Options: Ming-Image-0.1-Design

prompt

• Type: string
• Required
• Description: The prompt text used to describe the target image.

output_format

• Type: string
• Optional, default png
• Description: The output format of the generated image.
• Options: png, jpeg

response_format

• Type: string
• Optional, default b64_json
• Description: The format of the returned image.
• Options:
  • url — Returns an image URL. The URL is valid for 24 hours.
  • b64_json — Returns Base64-encoded image data.

size

• Type: string
• Optional, default auto
• Description: The output image size. Set to auto to let the model choose automatically; or specify it using the {w}x{h} format, such as "1024x1024".

watermark

• Type: boolean
• Optional, default false
• Description: Whether to add watermarks to AI-generated images.
• Options:
  • true — Enable the explicit watermark and implicit digital watermark generated by AI to comply with policy requirements.
  • false — Disable all watermarks.

Unsupported Parameters

The following OpenAI images/generations parameters are not supported by this interface:

• background
• moderation
• n
• output_compression
• partial_images
• quality
• style
• stream

Response Body

created

• Type: integer
• Description: Unix timestamp in seconds representing when the response was generated.

id

• Type: string
• Description: The unique identifier of this request.

model

• Type: string
• Description: The model ID used for this request.

data

• Type: object[]
• Description: The generated image list.

data[].b64_json

• Type: string
• Description: Base64-encoded image data, returned when response_format is b64_json.

data[].url

• Type: string
• Description: Image URL, returned when response_format is url. The URL is valid for 24 hours.

output_format

• Type: string
• Description: The image format of this response, such as png or jpeg.

size

• Type: string | null
• Description: The output image size. A concrete value such as 1024x512 is returned when it is explicitly specified; null is returned when it is not specified.

usage

• Type: object
• Description: Token and image-count usage statistics for this request. When billing is based on image count, use input_image_count and output_image_count.

usage.input_tokens

• Type: integer
• Description: Number of input tokens consumed.

usage.input_tokens_details

• Type: object
• Description: Breakdown of input tokens.
• Fields:
  • image_tokens — Number of tokens consumed by image input.
  • text_tokens — Number of tokens consumed by text input.

usage.output_tokens

• Type: integer
• Description: Number of output tokens generated.

usage.output_tokens_details

• Type: object
• Description: Breakdown of output tokens.
• Fields:
  • image_tokens — Number of tokens consumed by image output.
  • text_tokens — Number of tokens consumed by text output.

usage.total_tokens

• Type: integer
• Description: Total number of tokens consumed.

usage.input_image_count

• Type: integer
• Description: Number of input images in this request. Image generation always returns 0.

usage.output_image_count

• Type: integer
• Description: Number of output images generated in this request. This value is used for image-count billing.

Example

Request Example

curl --location --request POST \
  'https://api.ant-ling.com/v1/images/generations' \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "model": "Ming-Image-0.1-Design",
  "prompt": "Generate an apple"
}'

from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.ant-ling.com/v1",
    api_key="<YOUR_API_KEY>"
)
 
response = client.images.generate(
    model="Ming-Image-0.1-Design",
    prompt="Generate an apple"
)
 
print(response.data[0].b64_json)

import OpenAI from 'openai';
 
const client = new OpenAI({
  baseURL: 'https://api.ant-ling.com/v1',
  apiKey: '<YOUR_API_KEY>',
});
 
const response = await client.images.generate({
  model: 'Ming-Image-0.1-Design',
  prompt: 'Generate an apple',
});
 
console.log(response.data[0].b64_json);

Response Example

{
  "created": 1713833628,
  "id": "0b446a1717930916439978967edcf9",
  "model": "Ming-Image-0.1-Design",
  "data": [
    {
      "b64_json": "..."
    }
  ],
  "output_format": "png",
  "size": null,
  "usage": {
    "input_tokens": 0,
    "input_tokens_details": {
      "image_tokens": 0,
      "text_tokens": 0
    },
    "output_tokens": 4096,
    "output_tokens_details": {
      "image_tokens": 4096,
      "text_tokens": 0
    },
    "total_tokens": 4096,
    "input_image_count": 0,
    "output_image_count": 1
  }
}